March 26, 2024, 4:45 a.m. | Neelkamal Bhuyan, Debankur Mukherjee, Adam Wierman

cs.LG updates on arXiv.org arxiv.org

arXiv:2311.00181v2 Announce Type: replace-cross
Abstract: We study the smoothed online quadratic optimization (SOQO) problem where, at each round $t$, a player plays an action $x_t$ in response to a quadratic hitting cost and an additional squared $\ell_2$-norm cost for switching actions. This problem class has strong connections to a wide range of application domains including smart grid management, adaptive control, and data center management, where switching-efficient algorithms are highly sought after. We study the SOQO problem in both adversarial and …

abstract arxiv best of class cost cs.ds cs.lg math.oc math.pr norm optimization quadratic optimization study type

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne